Entity relation discovery from web tables and links

The World-Wide Web consists not only of a huge number of unstructured texts, but also a vast amount of valuable structured data. Web tables [2] are a typical type of structured information that are pervasive on the web, and Web-scale methods that automatically extract web tables have been studied extensively [1]. Many powerful systems (e.g.OCTOPUS [4], Mesa [3]) use extracted web tables as a fundamental component. In the database vernacular, a table is defined as a set of tuples which have the same attributes. Similarly, a web table is defined as a set of rows (corresponding to database tuples) which have the same column headers (corresponding to database attributes). Therefore, to extract a web table is to extract a relation on the web. In databases, tables often contain foreign keys which refer to other tables. Therefore, it follows that hyperlinks inside a web table sometimes function as foreign keys to other relations whose tuples are contained in the hyperlink's target pages. In this paper, we explore this idea by asking: can we discover new attributes for web tables by exploring hyperlinks inside web tables? This poster proposes a solution that takes a web table as input. Frequent patterns are generated as new candidate relations by following hyperlinks in the web table. The confidence of candidates are evaluated, and trustworthy candidates are selected to become new attributes for the table. Finally, we show the usefulness of our method by performing experiments on a variety of web domains.